Keita Sakuma

According to our database, Keita Sakuma authored at least 6 papers between 2023 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

Model Accuracy-Oriented Data Sets Visualization for Understanding Temporal Changes in Data.

Ryuta Matsuno, Keita Sakuma, Masakazu Hirokawa

Proceedings of the 28th International Conference Information Visualisation, 2024

Interactive Visualization of Ensemble Decision Trees Based on the Relations Among Weak Learners.

Miyu Kashiyama, Masakazu Hirokawa, Ryuta Matsuno, Keita Sakuma, Takayuki Itoh

Proceedings of the 28th International Conference Information Visualisation, 2024

eAIEDF: Extended AI Error Diagnosis Flowchart for Automatically Identifying Misprediction Causes in Production Models.

Keita Sakuma, Ryuta Matsuno, Yoshio Kameda

Proceedings of the 2024 IEEE/ACM 46th International Conference on Software Engineering: Companion Proceedings, 2024

2023

A Method of Identifying Causes of Prediction Errors to Accelerate MLOps.

Keita Sakuma, Ryuta Matsuno, Yoshio Kameda

Proceedings of the IEEE/ACM International Workshop on Deep Learning for Testing and Testing for Deep Learning, 2023

Quantitative Decomposition of Prediction Errors Revealing Multi-Cause Impacts: An Insightful Framework for MLOps.

Keita Sakuma, Ryuta Matsuno, Yoshio Kameda

Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, 2023

A Robust Backward Compatibility Metric for Model Retraining.

Ryuta Matsuno, Keita Sakuma

Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, 2023